Evolutionary graph structure learning for adversarial defense in GNNs

Graph Adversarial Defense with Virtual Spectral Anchor Injection

An active paradigm that repurposes the offensive tactic of node injection into a structural defense, ANIE significantly enhances GNN robustness, outperforming state-of-the-art defenses by up to 2× in classification accuracy under poisoning and evasion attacks.

Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networks

Graph Neural Networks (GNNs) have achieved remarkable performance in graph representation learning, yet their inherent vulnerability to adversarial attacks poses severe security risks. Especially, black-box node injection attacks have become a major threat to GNNs since they inject malicious nodes without altering the original graph topology. However, they typically decouple the generation of malicious node features and edge connections, thereby resulting in suboptimal attack efficacy under stringent budgets. To address this critical issue, this study proposes a novel Target-aware Interaction-guided Reinforcement learning for Black-box node injection Attacks on GNNs (TIRBA), which formulates the attack as a Markov Decision Process and jointly optimizes node feature generation and edge construction in a heterogeneous action space. Firstly, TIRBA designs a target-aware interaction encoder to fuse information of node features and edges. Further, it introduces a class-center guidance mechanism to utilize prior class distribution information, thereby guiding efficient exploration of the high-dimensional feature space. Finally, a topology difference-aware state value evaluation is adopted to explicitly capture local structural anomalies caused by injected nodes, thereby stabilizing the reinforcement learning training process. Experimental results demonstrate that the proposed TIRBA significantly outperforms state-of-the-art black-box node injection attack methods.

Cognitive Graph Intelligence for Adaptive and Robust DDoS Attack Detection in Next Generation Networks

By integrating temporal graph construction, adversarial augmentation, and GCN classification, GraphGAN effectively models coordinated attack behaviors and mitigates class imbalance, providing a robust and topology-aware solution for intrusion detection in data-constrained environments.

Defending against Model Extraction for GNNs with Model Reprogramming

This work proposes GraphRP (Graph Reprogramming Protection), a proactive defense framework that repurposes Model Reprogramming for security, and proves a lower bound on the attacker's estimation error that increases with the structural sensitivity of the reprogramming noise.

Adversarial Masked Graph Modeling for Robust Graph Autoencoders

Collateral Damage Constrained Backdoor Attacks on Graph Neural Networks